From dd467f92db404ca2e061889ad1b6dd6221390222 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 3 Dec 2024 11:20:50 +0100 Subject: mm/memory_hotplug: move debug_pagealloc_map_pages() into online_pages_range() In the near future, we want to have a single way to handover PageOffline pages to the buddy, whereby they could have: (a) Never been exposed to the buddy before: kept PageOffline when onlining the memory block. (b) Been allocated from the buddy, for example using alloc_contig_range() to then be set PageOffline, Let's start by making generic_online_page()->__free_pages_core() less special compared to ordinary page freeing (e.g., free_contig_range()), and perform the debug_pagealloc_map_pages() call unconditionally, even when the online callback might decide to keep the pages offline. All pages are already initialized with PageOffline, so nobody touches them either way. Link: https://lkml.kernel.org/r/20241203102050.223318-1-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Oscar Salvador Signed-off-by: Andrew Morton --- mm/memory_hotplug.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c43b4e7fb298..20af14e695c7 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -650,6 +650,7 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) * this and the first chunk to online will be pageblock_nr_pages. */ for (pfn = start_pfn; pfn < end_pfn;) { + struct page *page = pfn_to_page(pfn); int order; /* @@ -664,7 +665,14 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages) else order = MAX_PAGE_ORDER; - (*online_page_callback)(pfn_to_page(pfn), order); + /* + * Exposing the page to the buddy by freeing can cause + * issues with debug_pagealloc enabled: some archs don't + * like double-unmappings. So treat them like any pages that + * were allocated from the buddy. + */ + debug_pagealloc_map_pages(page, 1 << order); + (*online_page_callback)(page, order); pfn += (1UL << order); } -- cgit v1.2.3 From b9e40605daa94ae1817ceb5ce9e9b34093c6d850 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 3 Dec 2024 10:47:28 +0100 Subject: mm/page_isolation: don't pass gfp flags to start_isolate_page_range() The parameter is unused, so let's stop passing it. Link: https://lkml.kernel.org/r/20241203094732.200195-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Zi Yan Reviewed-by: Vlastimil Babka Reviewed-by: Oscar Salvador Reviewed-by: Vishal Moola (Oracle) Cc: Christophe Leroy Cc: Madhavan Srinivasan Cc: Michael Ellerman Cc: Naveen N Rao Cc: Nicholas Piggin Signed-off-by: Andrew Morton --- include/linux/page-isolation.h | 2 +- mm/memory_hotplug.c | 3 +-- mm/page_alloc.c | 2 +- mm/page_isolation.c | 4 +--- 4 files changed, 4 insertions(+), 7 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 73dc2c1841ec..898bb788243b 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -31,7 +31,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page, int migratetype); int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int flags, gfp_t gfp_flags); + int migratetype, int flags); void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, int migratetype); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 20af14e695c7..5f497ccf473d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -2000,8 +2000,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, - MEMORY_OFFLINE | REPORT_FAILURE, - GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL); + MEMORY_OFFLINE | REPORT_FAILURE); if (ret) { reason = "failure to isolate range"; goto failed_removal_pcplists_disabled; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 75de3711784e..98ffcd2bf153 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6447,7 +6447,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end, * put back to page allocator so that buddy can use them. */ - ret = start_isolate_page_range(start, end, migratetype, 0, gfp_mask); + ret = start_isolate_page_range(start, end, migratetype, 0); if (ret) goto done; diff --git a/mm/page_isolation.c b/mm/page_isolation.c index e680d40d96de..c608e9d72865 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -442,8 +442,6 @@ failed: * and PageOffline() pages. * REPORT_FAILURE - report details about the failure to * isolate the range - * @gfp_flags: GFP flags used for migrating pages that sit across the - * range boundaries. * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the @@ -476,7 +474,7 @@ failed: * Return: 0 on success and -EBUSY if any part of range cannot be isolated. */ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, - int migratetype, int flags, gfp_t gfp_flags) + int migratetype, int flags) { unsigned long pfn; struct page *page; -- cgit v1.2.3 From a684d59a323834c7483a40e21b75d14063771c58 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Thu, 5 Dec 2024 10:05:08 +0100 Subject: mm/memory_hotplug: don't use __GFP_HARDWALL when migrating pages via memory offlining We'll migrate pages allocated by other context; respecting the cpuset of the memory offlining context when allocating a migration target does not make sense. Drop the __GFP_HARDWALL by using GFP_KERNEL. Note that in an ideal world, migration code could figure out the cpuset of the original context and take that into consideration. Link: https://lkml.kernel.org/r/20241205090508.2095225-3-david@redhat.com Signed-off-by: David Hildenbrand Suggested-by: Vlastimil Babka Reviewed-by: Vlastimil Babka Acked-by: Oscar Salvador Cc: Zi Yan Signed-off-by: Andrew Morton --- mm/memory_hotplug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 5f497ccf473d..3b6f93962481 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1838,7 +1838,7 @@ put_folio: nodemask_t nmask = node_states[N_MEMORY]; struct migration_target_control mtc = { .nmask = &nmask, - .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, + .gfp_mask = GFP_KERNEL | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, .reason = MR_MEMORY_HOTPLUG, }; int ret; -- cgit v1.2.3 From 44d46b76c3a4b514a0cc9dab147ed430e5c1d699 Mon Sep 17 00:00:00 2001 From: Gregory Price Date: Fri, 20 Dec 2024 16:07:09 -0500 Subject: mm: add build-time option for hotplug memory default online type Memory hotplug presently auto-onlines memory into a zone the kernel deems appropriate if CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y. The memhp_default_state boot param enables runtime config, but it's not possible to do this at build-time. Remove CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE, and replace it with CONFIG_MHP_DEFAULT_ONLINE_TYPE_* choices that sync with the boot param. Selections: CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE => mhp_default_online_type = "offline" Memory will not be onlined automatically. CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO => mhp_default_online_type = "online" Memory will be onlined automatically in a zone deemed. appropriate by the kernel. CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL => mhp_default_online_type = "online_kernel" Memory will be onlined automatically. The zone may allow kernel data (e.g. ZONE_NORMAL). CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE => mhp_default_online_type = "online_movable" Memory will be onlined automatically. The zone will be ZONE_MOVABLE. Default to CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE to match the existing default CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=n behavior. Existing users of CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y should use CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO. [gourry@gourry.net: update KConfig comments] Link: https://lkml.kernel.org/r/20241226182918.648799-1-gourry@gourry.net Link: https://lkml.kernel.org/r/20241220210709.300066-1-gourry@gourry.net Signed-off-by: Gregory Price Acked-by: David Hildenbrand Cc: Greg Kroah-Hartman Cc: Huacai Chen Cc: Jonathan Corbet Cc: Oscar Salvador Cc: "Rafael J. Wysocki" Cc: WANG Xuerui Signed-off-by: Andrew Morton --- Documentation/admin-guide/kernel-parameters.txt | 4 +- Documentation/admin-guide/mm/memory-hotplug.rst | 4 +- arch/loongarch/configs/loongson3_defconfig | 5 ++- drivers/base/memory.c | 4 +- include/linux/memory_hotplug.h | 5 ++- mm/Kconfig | 57 ++++++++++++++++++++++--- mm/memory_hotplug.c | 33 +++++++++++--- 7 files changed, 89 insertions(+), 23 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index c79691eee54f..9138fcd18260 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3351,8 +3351,8 @@ [KNL] Set the initial state for the memory hotplug onlining policy. If not specified, the default value is set according to the - CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config - option. + CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel config + options. See Documentation/admin-guide/mm/memory-hotplug.rst. memmap=exactmap [KNL,X86,EARLY] Enable setting of an exact diff --git a/Documentation/admin-guide/mm/memory-hotplug.rst b/Documentation/admin-guide/mm/memory-hotplug.rst index cb2c080f400c..33c886f3d198 100644 --- a/Documentation/admin-guide/mm/memory-hotplug.rst +++ b/Documentation/admin-guide/mm/memory-hotplug.rst @@ -280,8 +280,8 @@ The following files are currently defined: blocks; configure auto-onlining. The default value depends on the - CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel configuration - option. + CONFIG_MHP_DEFAULT_ONLINE_TYPE kernel configuration + options. See the ``state`` property of memory blocks for details. ``block_size_bytes`` read-only: the size in bytes of a memory block. diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 4dffc90192f7..1cc6e8843680 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -113,7 +113,10 @@ CONFIG_ZBUD=y CONFIG_ZSMALLOC=m # CONFIG_COMPAT_BRK is not set CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE=y +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE is not set +CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO=y +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL is not set +# CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE is not set CONFIG_MEMORY_HOTREMOVE=y CONFIG_KSM=y CONFIG_TRANSPARENT_HUGEPAGE=y diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 67858eeb92ed..348c5dbbfa68 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -512,7 +512,7 @@ static ssize_t auto_online_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", - online_type_to_str[mhp_default_online_type]); + online_type_to_str[mhp_get_default_online_type()]); } static ssize_t auto_online_blocks_store(struct device *dev, @@ -524,7 +524,7 @@ static ssize_t auto_online_blocks_store(struct device *dev, if (online_type < 0) return -EINVAL; - mhp_default_online_type = online_type; + mhp_set_default_online_type(online_type); return count; } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index b27ddce5d324..eaac5ae8c05c 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -144,8 +144,6 @@ extern u64 max_mem_size; extern int mhp_online_type_from_str(const char *str); -/* Default online_type (MMOP_*) when new memory blocks are added. */ -extern int mhp_default_online_type; /* If movable_node boot option specified */ extern bool movable_node_enabled; static inline bool movable_node_is_enabled(void) @@ -303,6 +301,9 @@ static inline void __remove_memory(u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ #ifdef CONFIG_MEMORY_HOTPLUG +/* Default online_type (MMOP_*) when new memory blocks are added. */ +extern int mhp_get_default_online_type(void); +extern void mhp_set_default_online_type(int online_type); extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat); extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags); diff --git a/mm/Kconfig b/mm/Kconfig index 7949ab121070..1b501db06417 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -550,20 +550,63 @@ menuconfig MEMORY_HOTPLUG if MEMORY_HOTPLUG -config MEMORY_HOTPLUG_DEFAULT_ONLINE - bool "Online the newly added memory blocks by default" - depends on MEMORY_HOTPLUG +choice + prompt "Memory Hotplug Default Online Type" + default MHP_DEFAULT_ONLINE_TYPE_OFFLINE help + Default memory type for hotplugged memory. + This option sets the default policy setting for memory hotplug onlining policy (/sys/devices/system/memory/auto_online_blocks) which determines what happens to newly added memory regions. Policy setting can always be changed at runtime. + + The default is 'offline'. + + Select offline to defer onlining to drivers and user policy. + Select auto to let the kernel choose what zones to utilize. + Select online_kernel to generally allow kernel usage of this memory. + Select online_movable to generally disallow kernel usage of this memory. + + Example kernel usage would be page structs and page tables. + See Documentation/admin-guide/mm/memory-hotplug.rst for more information. - Say Y here if you want all hot-plugged memory blocks to appear in - 'online' state by default. - Say N here if you want the default policy to keep all hot-plugged - memory blocks in 'offline' state. +config MHP_DEFAULT_ONLINE_TYPE_OFFLINE + bool "offline" + help + Hotplugged memory will not be onlined by default. + Choose this for systems with drivers and user policy that + handle onlining of hotplug memory policy. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO + bool "auto" + help + Select this if you want the kernel to automatically online + hotplugged memory into the zone it thinks is reasonable. + This memory may be utilized for kernel data. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL + bool "kernel" + help + Select this if you want the kernel to automatically online + hotplugged memory into a zone capable of being used for kernel + data. This typically means ZONE_NORMAL. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE + bool "movable" + help + Select this if you want the kernel to automatically online + hotplug memory into ZONE_MOVABLE. This memory will generally + not be utilized for kernel data. + + This should only be used when the admin knows sufficient + ZONE_NORMAL memory is available to describe hotplug memory, + otherwise hotplug memory may fail to online. For example, + sufficient kernel-capable memory (ZONE_NORMAL) must be + available to allocate page structs to describe ZONE_MOVABLE. + +endchoice config MEMORY_HOTREMOVE bool "Allow for memory hot remove" diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3b6f93962481..e3655f07dd6e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -219,11 +219,30 @@ void put_online_mems(void) bool movable_node_enabled = false; -#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE -int mhp_default_online_type = MMOP_OFFLINE; -#else -int mhp_default_online_type = MMOP_ONLINE; -#endif +static int mhp_default_online_type = -1; +int mhp_get_default_online_type(void) +{ + if (mhp_default_online_type >= 0) + return mhp_default_online_type; + + if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_OFFLINE)) + mhp_default_online_type = MMOP_OFFLINE; + else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO)) + mhp_default_online_type = MMOP_ONLINE; + else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL)) + mhp_default_online_type = MMOP_ONLINE_KERNEL; + else if (IS_ENABLED(CONFIG_MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE)) + mhp_default_online_type = MMOP_ONLINE_MOVABLE; + else + mhp_default_online_type = MMOP_OFFLINE; + + return mhp_default_online_type; +} + +void mhp_set_default_online_type(int online_type) +{ + mhp_default_online_type = online_type; +} static int __init setup_memhp_default_state(char *str) { @@ -1328,7 +1347,7 @@ static int check_hotplug_memory_range(u64 start, u64 size) static int online_memory_block(struct memory_block *mem, void *arg) { - mem->online_type = mhp_default_online_type; + mem->online_type = mhp_get_default_online_type(); return device_online(&mem->dev); } @@ -1575,7 +1594,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) merge_system_ram_resource(res); /* online pages if requested */ - if (mhp_default_online_type != MMOP_OFFLINE) + if (mhp_get_default_online_type() != MMOP_OFFLINE) walk_memory_blocks(start, size, NULL, online_memory_block); return ret; -- cgit v1.2.3